A Comprehensive Analysis of Risk-Based Access Control Models for IoT: Balancing Security, Adaptability, and Resource Efficiency

The Internet of Things (IoT) has revolutionized how devices connect and interact, but it also brings serious security challenges, especially in managing access control. Traditional models like Role-Based Access Control (RBAC) and Attribute-Based Access Control (ABAC) often fall short in the face of IoT’s dynamic and complex environments. This paper offers a comprehensive analysis of 14 risk-based access control models, evaluated across five key criteria: security effectiveness, scalability, resource efficiency, adaptability, and integration of AI and machine learning. Advanced models leveraging AI, fuzzy logic, and neuro-fuzzy systems demonstrate exceptional accuracy and adaptability but face many other resource demands and scalability challenges. Conversely, resource-efficient models often trade off security and adaptability. Our findings underscore the need for innovative hybrid solutions that balance these competing priorities. This study provides practical insights for IoT practitioners and policymakers while highlighting research gaps to inspire future advancements in risk-based access control for IoT systems.